Fix value(json_pointer, default) aborting under JSON_NOEXCEPTION

With exceptions disabled (JSON_NOEXCEPTION or -fno-exceptions),
value(const json_pointer&, default) called std::abort() for array
reference tokens that array_index() rejects with out_of_range.404/410:
indices too large to fit size_type, the empty token ("/"), and tokens
like "/1a". With exceptions enabled, the same tokens correctly yielded
the default value, because get_checked_or_null() relied on
JSON_TRY/JSON_INTERNAL_CATCH (detail::out_of_range&) to turn the
exception into nullptr; under JSON_NOEXCEPTION, JSON_THROW aborts
before that catch is ever reached.

get_checked_or_null() now detects those out-of-range tokens itself,
the same way contains(json_pointer) already does (#5495), and only
calls array_index() for tokens that must still raise parse_error.106
or parse_error.109 (e.g. "/01", "/+1"), matching the documented
behavior of value().

Added regression tests to tests/src/unit-disabled_exceptions.cpp
(built with JSON_NOEXCEPTION and -fno-exceptions) and the matching
checks to tests/src/unit-element_access2.cpp for normal exception
mode.

Fixes #5672.
Signed-off-by: Niels Lohmann <mail@nlohmann.me>

include/nlohmann/detail/json_pointer.hpp

@@ -678,19 +678,29 @@ class json_pointer
                         return nullptr;
                     }
 
-                    // may throw parse_error.106/109 for a malformed index; an
-                    // index that is syntactically valid but cannot be
-                    // represented (out_of_range.404/410) is treated like an
-                    // out-of-range index below
-                    typename BasicJsonType::size_type idx{};
-                    JSON_TRY
+                    // tokens that array_index() rejects with parse_error.106/109
+                    // are passed on to it; all other tokens that it would reject
+                    // with out_of_range.404/410 are detected here, so that this
+                    // also works without exceptions
+                    if (JSON_HEDLEY_UNLIKELY(reference_token.size() > 1 && !(reference_token[0] >= '1' && reference_token[0] <= '9')))
                     {
-                        idx = array_index<BasicJsonType>(reference_token);
+                        static_cast<void>(array_index<BasicJsonType>(reference_token)); // throws parse_error.106/109
                     }
-                    JSON_INTERNAL_CATCH (detail::out_of_range&)
+                    if (JSON_HEDLEY_UNLIKELY(reference_token.empty() || !std::all_of(reference_token.begin(), reference_token.end(), [](const char c)
+                {
+                    return c >= '0' && c <= '9';
+                })))
                     {
                         return nullptr;
                     }
+                    errno = 0; // strtoull() does not reset errno on success
+                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
+                    const unsigned long long magnitude = std::strtoull(reference_token.data(), &p_end, 10); // NOLINT(runtime/int)
+                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
+                    {
+                        return nullptr;
+                    }
+                    const auto idx = static_cast<typename BasicJsonType::size_type>(magnitude);
 
                     if (JSON_HEDLEY_UNLIKELY(idx >= ptr->m_data.m_value.array->size()))
                     {

single_include/nlohmann/json.hpp

@@ -19520,19 +19520,29 @@ class json_pointer
                         return nullptr;
                     }
 
-                    // may throw parse_error.106/109 for a malformed index; an
-                    // index that is syntactically valid but cannot be
-                    // represented (out_of_range.404/410) is treated like an
-                    // out-of-range index below
-                    typename BasicJsonType::size_type idx{};
-                    JSON_TRY
+                    // tokens that array_index() rejects with parse_error.106/109
+                    // are passed on to it; all other tokens that it would reject
+                    // with out_of_range.404/410 are detected here, so that this
+                    // also works without exceptions
+                    if (JSON_HEDLEY_UNLIKELY(reference_token.size() > 1 && !(reference_token[0] >= '1' && reference_token[0] <= '9')))
                     {
-                        idx = array_index<BasicJsonType>(reference_token);
+                        static_cast<void>(array_index<BasicJsonType>(reference_token)); // throws parse_error.106/109
                     }
-                    JSON_INTERNAL_CATCH (detail::out_of_range&)
+                    if (JSON_HEDLEY_UNLIKELY(reference_token.empty() || !std::all_of(reference_token.begin(), reference_token.end(), [](const char c)
+                {
+                    return c >= '0' && c <= '9';
+                })))
                     {
                         return nullptr;
                     }
+                    errno = 0; // strtoull() does not reset errno on success
+                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
+                    const unsigned long long magnitude = std::strtoull(reference_token.data(), &p_end, 10); // NOLINT(runtime/int)
+                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
+                    {
+                        return nullptr;
+                    }
+                    const auto idx = static_cast<typename BasicJsonType::size_type>(magnitude);
 
                     if (JSON_HEDLEY_UNLIKELY(idx >= ptr->m_data.m_value.array->size()))
                     {

tests/src/unit-disabled_exceptions.cpp

@@ -46,6 +46,21 @@ TEST_CASE("Tests with disabled exceptions")
         CHECK(*sax_no_exception::error_string == "[json.exception.parse_error.101] parse error at line 1, column 1: syntax error while parsing value - invalid literal; last read: 'x'");
         delete sax_no_exception::error_string; // NOLINT(cppcoreguidelines-owning-memory)
     }
+
+    SECTION("issue #5672 - value(json_pointer, default) must not abort for array tokens that are not a valid index")
+    {
+        const json j = {1, 2, 3};
+
+        // a syntactically valid index that is out of range for this array
+        CHECK(j.value("/7"_json_pointer, 42) == 42);
+        // a reference token that is not a number at all
+        CHECK(j.value("/1a"_json_pointer, 42) == 42);
+        // the empty reference token (JSON pointer "/")
+        CHECK(j.value("/"_json_pointer, 42) == 42);
+        // an index whose magnitude does not fit into size_type
+        CHECK(j.value("/99999999999999999999999"_json_pointer, 42) == 42);
+        CHECK(j.value("/18446744073709551615"_json_pointer, 42) == 42);
+    }
 }
 
 DOCTEST_GCC_SUPPRESS_WARNING_POP

tests/src/unit-element_access2.cpp

@@ -482,6 +482,21 @@ TEST_CASE_TEMPLATE("element access 2", Json, nlohmann::json, nlohmann::ordered_j
                     CHECK(j_array.value("/-"_json_pointer, 42) == 42);
                     CHECK(j_array_const.value("/-"_json_pointer, 42) == 42);
 
+                    // Test an index with a non-digit after a valid leading digit; this is
+                    // out_of_range (not parse_error) and must not throw (see #5672)
+                    CHECK(j_array.value("/1a"_json_pointer, 42) == 42);
+                    CHECK(j_array_const.value("/1a"_json_pointer, 42) == 42);
+
+                    // Test the empty reference token (JSON pointer "/"); see #5672
+                    CHECK(j_array.value("/"_json_pointer, 42) == 42);
+                    CHECK(j_array_const.value("/"_json_pointer, 42) == 42);
+
+                    // Test an index whose magnitude does not fit into size_type (see #5672)
+                    CHECK(j_array.value("/99999999999999999999999"_json_pointer, 42) == 42);
+                    CHECK(j_array_const.value("/99999999999999999999999"_json_pointer, 42) == 42);
+                    CHECK(j_array.value("/18446744073709551615"_json_pointer, 42) == 42);
+                    CHECK(j_array_const.value("/18446744073709551615"_json_pointer, 42) == 42);
+
 #if !defined(JSON_NOEXCEPTION)
                     // Test malformed index (non-numeric) throws parse_error
                     CHECK_THROWS_WITH_AS(j_array.value("/foo"_json_pointer, 1), "[json.exception.parse_error.109] parse error: array index 'foo' is not a number", typename Json::parse_error&);

tools/amalgamate/CHANGES.md

@@ -8,6 +8,3 @@ The following changes have been made to the code with respect to <https://github
   - membership check
   - made function from `_is_within`
   - removed unused variable `actual_path`
-- Added the optional config key `external`: include paths listed there are kept as
-  `#include` directives instead of being inlined (the first directive per path; the
-  repeated ones are commented out).

tools/amalgamate/README.md

@@ -57,11 +57,6 @@ Python v.2.7.0 or higher is required.
    amalgamation. Have a look at `test/source.c.json` and `test/include.h.json`
    to see two examples.
 
-   The optional `external` list names include paths that are kept as `#include`
-   directives instead of being inlined, e.g. `["nlohmann/json.hpp"]` for a header
-   that includes another amalgamated header. Only the first directive for each
-   of these paths is kept; the repeated ones are commented out.
-
  * The `-s, --source` option should specify the path to the source directory.
    This is useful for supporting separate source and build directories.
 

tools/amalgamate/amalgamate.py

@@ -62,10 +62,6 @@ class Amalgamation(object):
         return None
 
     def __init__(self, args):
-        # include paths that are kept as #include directives instead of
-        # being inlined (e.g. a header amalgamated on its own)
-        self.external = []
-        self.included_external = []
         with open(args.config, 'r') as f:
             config = json.loads(f.read())
             for key in config:
@@ -224,14 +220,11 @@ class TranslationUnit(object):
         while include_match:
             if not _is_within(include_match, skippable_contexts):
                 include_path = include_match.group("path")
-                if include_path in self.amalgamation.external:
-                    includes.append((include_match, None))
-                else:
-                    search_same_dir = include_match.group(1) == '"'
-                    found_included_path = self.amalgamation.find_included_file(
-                        include_path, self.file_dir if search_same_dir else None)
-                    if found_included_path:
-                        includes.append((include_match, found_included_path))
+                search_same_dir = include_match.group(1) == '"'
+                found_included_path = self.amalgamation.find_included_file(
+                    include_path, self.file_dir if search_same_dir else None)
+                if found_included_path:
+                    includes.append((include_match, found_included_path))
 
             include_match = self.include_pattern.search(self.content,
                                                         include_match.end())
@@ -242,17 +235,6 @@ class TranslationUnit(object):
         for include in includes:
             include_match, found_included_path = include
             tmp_content += self.content[prev_end:include_match.start()]
-            if found_included_path is None:
-                # an external header: keep the first directive and comment
-                # out the repeated ones
-                include_path = include_match.group("path")
-                if include_path in self.amalgamation.included_external:
-                    tmp_content += "// {0}".format(include_match.group(0))
-                else:
-                    self.amalgamation.included_external.append(include_path)
-                    tmp_content += include_match.group(0)
-                prev_end = include_match.end()
-                continue
             tmp_content += "// {0}\n".format(include_match.group(0))
             if found_included_path not in self.amalgamation.included_files:
                 t = TranslationUnit(found_included_path, self.amalgamation, False)

tools/amalgamate/config_json_view.json

@@ -1,9 +0,0 @@
-{
-	"project": "JSON for Modern C++",
-	"target": "single_include/nlohmann/json_view.hpp",
-	"sources": [
-		"include/nlohmann/json_view.hpp"
-	],
-	"include_paths": ["include"],
-	"external": ["nlohmann/json.hpp"]
-}